GLM-5.1
READER SUMMARYFlagship API model designed for sustained planning, execution, testing, repair, and long-horizon coding workflows.
Why this model scores 78.1
Developer-reported eight-hour closed-loop execution suggests high autonomy, but capability and persistence lack independent validation; public API access still creates meaningful deployment.
News tied to GLM-5.1
The model score of 78.1 rates this model's risk profile. The overall Doom Index of 62.1 measures the recalibrated complete evidence corpus. These values answer different questions.
Each article's leave-one-out Doom Index contribution is divided equally among the exact models named on that article. This prevents multi-model evidence from being claimed in full on several model pages. Model risk scores are recalculated from their technical profile and related news, but never feed back into the overall index.
Z.ai releases GLM-5.1 for eight-hour autonomous task execution
Z.ai released GLM-5.1 through its API with long-horizon planning, tool use, iterative testing, repair, and claimed autonomous execution lasting up to eight hours.
- Full item contribution
- +0.08
- GLM-5.1 equal share
- +0.08
Model score history
- R2Doom Score 78.1
Full-corpus evidence recalculated after run intensive-backfill-20260811-191225 under bounded-corpus-v2.
11 Aug 2026 - R1Doom Score 78.3
New exact version verified from dated official release notes and documentation.
11 Aug 2026